Unlock AI living guides
<main>
Agents
4 guidesThe Agent Maintenance Loop
A repeatable loop for inspecting an agent after launch across job, diet, memory, tools, reach, proof, and value, then deciding whether to keep, change, pause, or retire it.
Open guideFind a Real Job for Your First AI Agent
Turn one repeated frustration into a written Pain Note, a pattern you have checked yourself, an honest verdict on whether an agent belongs here, and a draft-only pilot you can measure.
The One-Minute Test
Route any task to chat, one accountable agent, a small agent team, or the manual path — in about a minute, with a next action for whichever route wins.
Automation Discovery
A downloadable agent skill that reads your real work traces, audits the evidence, and offers 2–5 automations you can verify against your own history. You pick; it builds and proves only that.
Codex
4 guidesInstall OpenAI's Codex app, set up real projects, and run an AI-first workflow where every move ships with a copy-paste prompt. Files, Side chat, Review, Terminal, and Browser: the panel that turns Codex from a chat box into a workbench. Click any element, attach a note or screenshot, and steer Codex from inside the page you are building. Threads, child threads, steering versus queueing, and the workspace habits that keep long-running agent work sane.The Ultimate Guide to Codex
Codex side panel deep-dive
Codex browser & annotations
Codex threading & child threads
General
13 guidesSkills are folders of plain text. Watch a real one work, download it, read it with your own eyes, and rewrite the lines that were never yours. A practical routing guide for Open Skills, Open Brain, and Open Engine: diagnose the bottleneck, choose where to start, and personalize the stack. What Open Brain is, how the one-database memory layer works, and the 30-minute, zero-code path to building yours — with the full guide on GitHub. Run ultracode-style multi-agent swarms on inexpensive models: your best model plans and reviews, cheap cross-model workers implement in parallel, and exit codes decide what passed. Give a Chinese model and your current model the same real job, the same sources, and the same pass/fail check, then see which one earns the work. Find the hidden setup shaping your AI, see what protects your work and what creates drag, and clean it safely with numbered approval and full rollback. Claude and Codex editions. Track where your tokens go across Codex, Claude, and ChatGPT, then use the burn rate as a fluency signal. Assemble Open Skills primitives into an agent that turns your denial letter, EOB, and plan documents into a cited appeal packet. Use the same document-grounded primitives to turn your tax documents and real IRS sources into a structured, CPA-ready prep packet. Point the same document-grounded primitives at your inbox: a live MCP ingest loop that reconstructs threads, keeps a commitments ledger, and drafts cited follow-ups that stop at the send boundary. Download Gemma 4 E2B in LM Studio, save a tested redaction system prompt as a preset, and turn documents you can't upload into proposed redacted copies — offline, on your own machine. Install AI Airlock on an Apple Silicon Mac, review what it removes, seal a verified working copy, and use that copy with ChatGPT, Claude, or another AI tool. What each move saves, why it works, and what proves it — from editing a bad turn instead of correcting it, to turning exact work into code, to the free Token Saver skill. One matched job went from 51,712 reused input tokens to zero.Make Any Skill Your Own
Open Stack
Open Brain — one memory, every AI
Ringer — swarm power without the frontier bill
How to Run a Chinese-Model Bakeoff in Ringer
Clean My AI Harness
Build your own token-burn dashboard
Build a Healthcare Claim Appeals Agent
Build a Tax Prep Organizer Agent
Build an Email Follow-Up Agent
Clean Sensitive Docs with a Local Model
AI Airlock: Use AI Without Leaking Sensitive Documents
15 Ways to Cut Token Waste in Codex and Claude